© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 3281
    Prev
    Next
    INDEX
    Explanations

    attributes of strength and capability in individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.02
    1:0.01
    2:0.33
    3:0.06
    4:0.17
    5:0.02
    6:0.04
    7:0.12
    8:0.05
    9:0.02
    10:0.05
    11:0.05
    Negative Logits
    izen
    -1.58
    itsch
    -1.48
    Topic
    -1.47
    ¶
    -1.46
    Reviewer
    -1.45
    Return
    -1.44
    �
    -1.41
    ="#
    -1.40
    �
    -1.37
    JP
    -1.37
    POSITIVE LOGITS
     necessary
    1.49
     comfortably
    1.43
     requisite
    1.39
     minus
    1.38
     perfected
    1.34
     comfortable
    1.34
     Messi
    1.29
     Moreno
    1.28
    velt
    1.24
     desired
    1.22
    Activations Density 0.320%

    No Known Activations